© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 27-TRANSCODER-HP
    7. 9034
    Prev
    Next
    INDEX
    Explanations

    technical jargon

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    utils
    -0.29
    çĴĭ
    -0.27
    Ò»
    -0.27
     hap
    -0.26
    Utils
    -0.26
     Widgets
    -0.26
     utils
    -0.25
    æ¯ģ
    -0.25
    ooks
    -0.24
    iece
    -0.24
    POSITIVE LOGITS
    åħħæĸ¥
    0.31
    顾éĹ®
    0.30
     planet
    0.26
    etat
    0.25
    _gas
    0.25
    太空
    0.25
    rück
    0.25
    _conversion
    0.25
     gas
    0.25
    å®ĩå®Ļ
    0.25
    Activations Density 0.003%

    No Known Activations